基于时空轨迹嵌套图谱的患者异常行为识别方法及系统
By constructing a spatiotemporal trajectory nested map, the problem of insufficient spatiotemporal feature extraction in the behavioral monitoring of patients with cognitive impairment in existing technologies is solved. This enables individualized behavioral recognition and anomaly detection, reduces false alarm and false negative rates, and improves the reliability and interpretability of monitoring.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- 四川互慧软件有限公司
- Filing Date
- 2026-04-10
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies lack the ability to extract spatiotemporal features when monitoring the behavior of patients with cognitive impairment, leading to false alarms or missed alarms and failing to meet the needs of individualized monitoring. Furthermore, traditional methods rely on spatial constraint strategies and cannot effectively characterize structural changes in trajectories.
By constructing a method based on spatiotemporal trajectory nesting maps, including trajectory sequence preprocessing, location node identification, periodic trajectory map construction, merging of multi-period spatiotemporal trajectory nesting maps, and behavioral pattern similarity analysis, individualized monitoring of the behavior of patients with cognitive impairment can be achieved.
It enhances the ability to characterize the behavioral patterns of patients with cognitive impairment, significantly reduces false alarm and false negative rates, provides interpretable abnormal monitoring results, and facilitates individualized care management.
Smart Images
Figure CN122020068B_ABST